• Ocean and Polar Research
• /
• v.42 no.3
• /
• pp.179-194
• /
• 2020

The present study aims to evaluate the effects of satellite-based SST (OSTIA) assimilation on a regional ocean circulation model for the Yellow and East China Seas (YECS), using three different assimilation methods: the Ensemble Optimal Interpolation (EnOI), Ensemble Kalman Filter (EnKF), and 4-Dimensional Variational (4DVAR) techniques, which are widely used in the ocean modeling communities. The model experiments show that an improved initial condition by assimilating the SST affects the seasonal water temperature and water mass distributions of the YECS. In particular, the SST data assimilation influences the temperature structures horizontally and vertically in winter, thereby improving the behavior of the YS warm current water. This is due to the fact that during wintertime the water column is well mixed, which is directly updated by the SST assimilation. The model comparisons indicate that the SST assimilation can improve the model performance in resolving the subsurface structures in wintertime, but has a relatively small impact in summertime due to the strong stratification. The differences among the different assimilation experiments are obvious when the SST was sharply changed due to a typhoon passage. Overall, the EnKF and 4DVAR show better agreement with the observations than the EnOI. The relatively low performance of EnOI under storm conditions may be related with a limitation of EnOI method whereby an analysis is obtained from a number of climatological fields, and thus the typhoon-induced SST changes in short-time scales may not be adequately reflected in the data assimilation.

• Atmosphere
• /
• v.24 no.3
• /
• pp.403-417
• /
• 2014

Future changes in seasonal mean temperature and precipitation over East Asia under anthropogenic global warming are investigated by comparing the historical run for 1979~2005 and the Representative Concentration Pathway (RCP) 4.5 run for 2006~2100 with 20 coupled models which participated in the phase five of Coupled Model Inter-comparison Project (CMIP5). Although an increase in future temperature over the East Asian monsoon region has been commonly accepted, the prediction of future precipitation under global warming still has considerable uncertainties with a large inter-model spread. Thus, we select best five models, based on the evaluation of models' performance in present climate for boreal summer and winter seasons, to reduce uncertainties in future projection. Overall, the CMIP5 models better simulate climatological temperature and precipitation over East Asia than the phase 3 of CMIP and the five best models' multi-model ensemble (B5MME) has better performance than all 20 models' multi-model ensemble (MME). Under anthropogenic global warming, significant increases are expected in both temperature and land-ocean thermal contrast over the entire East Asia region during both seasons for near and long term future. The contrast of future precipitation in winter between land and ocean will decrease over East Asia whereas that in summer particularly over the Korean Peninsula, associated with the Changma, will increase. Taking into account model validation and uncertainty estimation, this study has made an effort on providing a more reliable range of future change for temperature and precipitation particularly over the Korean Peninsula than previous studies.

• Smart Media Journal
• /
• v.11 no.8
• /
• pp.65-72
• /
• 2022

Due to COVID-19, the importance of non-face-to-face counseling is increasing as the face-to-face counseling method has progressed to non-face-to-face counseling. The advantage of non-face-to-face counseling is that it can be consulted online anytime, anywhere and is safe from COVID-19. However, it is difficult to understand the client's mind because it is difficult to communicate with non-verbal expressions. Therefore, it is important to recognize emotions by accurately analyzing text and voice in order to understand the client's mind well during non-face-to-face counseling. Therefore, in this paper, text data is vectorized using FastText after separating consonants, and voice data is vectorized by extracting features using Log Mel Spectrogram and MFCC respectively. We propose a multi-emotion recognition model that recognizes five emotions using vectorized data using an LSTM model. Multi-emotion recognition is calculated using RMSE. As a result of the experiment, the RMSE of the proposed model was 0.2174, which was the lowest error compared to the model using text and voice data, respectively.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.11
• /
• pp.53-63
• /
• 2023

This study developed a cognitive impairment predictive model as one of the screening tests for preventing dementia in the elderly by using Automated Machine Learning(AutoML). We used 'Wearable lifelog data for high-risk dementia patients' of National Information Society Agency, then conducted using PyCaret 3.0.0 in the Google Colaboratory environment. This study analysis steps are as follows; first, selecting five models demonstrating excellent classification performance for the model development and lifelog data analysis. Next, using ensemble learning to integrate these models and assess their performance. It was found that Voting Classifier, Gradient Boosting Classifier, Extreme Gradient Boosting, Light Gradient Boosting Machine, Extra Trees Classifier, and Random Forest Classifier model showed high predictive performance in that order. This study findings, furthermore, emphasized on the the crucial importance of 'Average respiration per minute during sleep' and 'Average heart rate per minute during sleep' as the most critical feature variables for accurate predictions. Finally, these study results suggest that consideration of the possibility of using machine learning and lifelog as a means to more effectively manage and prevent cognitive impairment in the elderly.

• Journal of Korea Water Resources Association
• /
• v.51 no.11
• /
• pp.1031-1041
• /
• 2018

ANFIS-based methodology for improving GloSea5 ensemble weather forecast is developed and evaluated in this study. The proposed method consists of two steps: pre & post processing. For ensemble prediction of GloSea5, weights are assigned to the ensemble members based on Optimal Weighting Method (OWM) in the pre-processing. Then, the bias of the results of pre-processed is corrected based on Model Output Statistics (MOS) method in the post-processing. The watershed of the Chungju multi-purpose dam in South Korea is selected as a study area. The results of evaluation indicated that the pre-processing step (CASE1), the post-processing step (CASE2), pre & post processing step (CASE3) results were significantly improved than the original GloSea5 bias correction (BC_GS5). Correction performance is better the order of CASE3, CASE1, CASE2. Also, the accuracy of pre-processing was improved during the season with high variability of precipitation. The post-processing step reduced the error that could not be smoothed by pre-processing step. It could be concluded that this methodology improved the ability of GloSea5 ensemble weather forecast by using ANFIS, especially, for the summer season with high variability of precipitation when applied both pre- and post-processing steps.

• Structural Engineering and Mechanics
• /
• v.70 no.5
• /
• pp.513-524
• /
• 2019

This study proposed an improved particle swarm optimization (IPSO) method ensemble with kriging model for model updating. By introducing genetic algorithm (GA) and grouping strategy together with elite selection into standard particle optimization (PSO), the IPSO is obtained. Kriging metamodel serves for predicting the structural responses to avoid complex computation via finite element model. The combination of IPSO and kriging model shall provide more accurate searching results and obtain global optimal solution for model updating compared with the PSO, Simulate Annealing PSO (SimuAPSO), BreedPSO and PSOGA. A plane truss structure and ASCE Benchmark frame structure are adopted to verify the proposed approach. The results indicated that the hybrid of kriging model and IPSO could serve for model updating effectively and efficiently. The updating results further illustrated that IPSO can provide superior convergent solutions compared with PSO, SimuAPSO, BreedPSO and PSOGA.

• Journal of Korea Water Resources Association
• /
• v.57 no.2
• /
• pp.127-137
• /
• 2024

Physical models, which are often used for water resource management, are difficult to build and operate with input data and may involve the subjective views of users. In recent years, research using data-driven models such as machine learning has been actively conducted to compensate for these problems in the field of water resources, and in this study, an artificial neural network was used to simulate long-term rainfall runoff in the Osipcheon watershed in Samcheok-si, Gangwon-do. For this purpose, three input data groups (meteorological observations, daily precipitation and potential evapotranspiration, and daily precipitation - potential evapotranspiration) were constructed from meteorological data, and the results of training the LSTM (Long Short-term Memory) artificial neural network model were compared and analyzed. As a result, the performance of LSTM-Model 1 using only meteorological observations was the highest, and six LSTM-MLP ensemble models with MLP artificial neural networks were built to simulate long-term runoff in the Fifty Thousand Watershed. The comparison between the LSTM and LSTM-MLP models showed that both models had generally similar results, but the MAE, MSE, and RMSE of LSTM-MLP were reduced compared to LSTM, especially in the low-flow part. As the results of LSTM-MLP show an improvement in the low-flow part, it is judged that in the future, in addition to the LSTM-MLP model, various ensemble models such as CNN can be used to build physical models and create sulfur curves in large basins that take a long time to run and unmeasured basins that lack input data.

• Atmosphere
• /
• v.25 no.3
• /
• pp.529-541
• /
• 2015

Korea Institute of Atmospheric Prediction System (KIAPS) has been developing a global numerial prediction model and data assimilation system. We has implemented LETKF (Local Ensemble Transform Kalman Filter, Hunt et al., 2007) data assimilation system to NCAR CAM-SE (National Center for Atmospheric Research Community Atmosphere Model with Spectral Element dynamical core, Dennis et al., 2012) that has cubed-sphere grid, known as the same grid system of KIAPS Integrated Model (KIM) now developing. In this study, we have assimilated Global Positioning System Radio Occultation (GPS-RO) bending angle measurements in addition to conventional data within ensemble-based data assimilation system. Before assimilating bending angle data, we performed a vertical unit conversion. The information of vertical localization for GPS-RO data is given by the unit of meter, but the vertical localization method in the LETKF system is based on pressure unit. Therefore, with a clever conversion of the vertical information, we have conducted experiments to search for the best vertical localization scale on GPS-RO data under the Observing System Simulation Experiments (OSSEs). As a result, we found the optimal setting of vertical localization for the GPS-RO bending angle data assimilation. We plan to apply the selected localization strategy to the LETKF system implemented to KIM which is expected to give better analysis of GPS-RO data assimilation due to much higher model top.

• Atmosphere
• /
• v.26 no.1
• /
• pp.35-45
• /
• 2016

Initialization of the global seasonal forecast system is as much important as the quality of the embedded climate model for the climate prediction in sub-seasonal time scale. Recent studies have emphasized the important role of soil moisture initialization, suggesting a significant increase in the prediction skill particularly in the mid-latitude land area where the influence of sea surface temperature in the tropics is less crucial and the potential predictability is supplemented by land-atmosphere interaction. This study developed a new soil moisture initialization method applicable to the KMA operational seasonal forecasting system. The method includes first the long-term integration of the offline land surface model driven by observed atmospheric forcing and precipitation. This soil moisture reanalysis is given for the initial state in the ensemble seasonal forecasts through a simple anomaly initialization technique to avoid the simulation drift caused by the systematic model bias. To evaluate the impact of the soil moisture initialization, two sets of long-term, 10-member ensemble experiment runs have been conducted for 1996~2009. As a result, the soil moisture initialization improves the prediction skill of surface air temperature significantly at the zero to one month forecast lead (up to ~60 days forecast lead), although the skill increase in precipitation is less significant. This study suggests that improvements of the prediction in the sub-seasonal timescale require the improvement in the quality of initial data as well as the adequate treatment of the model systematic bias.

• Journal of the Korean Geosynthetics Society
• /
• v.19 no.1
• /
• pp.45-53
• /
• 2020

There is an increasing tendency to try to make predictive analysis using measurement data based on machine learning techniques in the railway industries. In this paper, it was predicted that Track quality index (TQI) using vehicle acceleration data based on the machine learning method. The XGB (XGBoost) was the most accurate with 85% in the all data sets. Unlike the SVM model with a single algorithm, the RF and XGB model with a ensemble system were considered to be good at the prediction performance. In the case of the Surface TQI, it is shown that the acceleration of the z axis is highly related to the vertical direction and is in good agreement with the previous studies. Therefore, it is appropriate to apply the model with the ensemble algorithm to predict the track quality index using the vehicle vibration acceleration data because the accuracy may vary depending on the applied model in the machine learning methods.